1 | ###########################################################################
|
---|
2 | #
|
---|
3 | # ExcelPlugin.pm -- plugin for importing Microsoft Excel files.
|
---|
4 | # (currently only versions 95 and 97)
|
---|
5 | #
|
---|
6 | # A component of the Greenstone digital library software
|
---|
7 | # from the New Zealand Digital Library Project at the
|
---|
8 | # University of Waikato, New Zealand.
|
---|
9 | #
|
---|
10 | # Copyright (C) 2002 New Zealand Digital Library Project
|
---|
11 | #
|
---|
12 | # This program is free software; you can redistribute it and/or modify
|
---|
13 | # it under the terms of the GNU General Public License as published by
|
---|
14 | # the Free Software Foundation; either version 2 of the License, or
|
---|
15 | # (at your option) any later version.
|
---|
16 | #
|
---|
17 | # This program is distributed in the hope that it will be useful,
|
---|
18 | # but WITHOUT ANY WARRANTY; without even the implied warranty of
|
---|
19 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
---|
20 | # GNU General Public License for more details.
|
---|
21 | #
|
---|
22 | # You should have received a copy of the GNU General Public License
|
---|
23 | # along with this program; if not, write to the Free Software
|
---|
24 | # Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
|
---|
25 | #
|
---|
26 | ###########################################################################
|
---|
27 |
|
---|
28 | package ExcelPlugin;
|
---|
29 |
|
---|
30 | use ConvertBinaryFile;
|
---|
31 | use strict;
|
---|
32 | no strict 'refs'; # allow filehandles to be variables and viceversa
|
---|
33 |
|
---|
34 | sub BEGIN {
|
---|
35 | @ExcelPlugin::ISA = ('ConvertBinaryFile');
|
---|
36 | }
|
---|
37 |
|
---|
38 | my $arguments =
|
---|
39 | [ { 'name' => "process_exp",
|
---|
40 | 'desc' => "{BasePlugin.process_exp}",
|
---|
41 | 'type' => "regexp",
|
---|
42 | 'reqd' => "no",
|
---|
43 | 'deft' => &get_default_process_exp() }
|
---|
44 | ];
|
---|
45 |
|
---|
46 | my $options = { 'name' => "ExcelPlugin",
|
---|
47 | 'desc' => "{ExcelPlugin.desc}",
|
---|
48 | 'abstract' => "no",
|
---|
49 | 'inherits' => "yes",
|
---|
50 | 'srcreplaceable' => "yes", # Source docs in Excel format can be replaced with GS-generated html
|
---|
51 | 'args' => $arguments };
|
---|
52 |
|
---|
53 | sub new {
|
---|
54 | my ($class) = shift (@_);
|
---|
55 | my ($pluginlist,$inputargs,$hashArgOptLists) = @_;
|
---|
56 | push(@$pluginlist, $class);
|
---|
57 |
|
---|
58 | if(defined $arguments){ push(@{$hashArgOptLists->{"ArgList"}},@{$arguments});}
|
---|
59 | if(defined $options) { push(@{$hashArgOptLists->{"OptList"}},$options)};
|
---|
60 |
|
---|
61 | my $self = new ConvertBinaryFile($pluginlist, $inputargs, $hashArgOptLists);
|
---|
62 |
|
---|
63 | if ($self->{'info_only'}) {
|
---|
64 | # don't worry about any options etc
|
---|
65 | return bless $self, $class;
|
---|
66 | }
|
---|
67 |
|
---|
68 | $self->{'filename_extension'} = "xls";
|
---|
69 | $self->{'file_type'} = "Excel";
|
---|
70 |
|
---|
71 | my $secondary_plugin_options = $self->{'secondary_plugin_options'};
|
---|
72 | if (!defined $secondary_plugin_options->{'HTMLPlugin'}) {
|
---|
73 | $secondary_plugin_options->{'HTMLPlugin'} = [];
|
---|
74 | }
|
---|
75 | my $html_options = $secondary_plugin_options->{'HTMLPlugin'};
|
---|
76 |
|
---|
77 | push(@$html_options, "-input_encoding", "utf8");
|
---|
78 | push(@$html_options,"-extract_language") if $self->{'extract_language'};
|
---|
79 | $self = bless $self, $class;
|
---|
80 |
|
---|
81 | $self->load_secondary_plugins($class,$secondary_plugin_options,$hashArgOptLists);
|
---|
82 | return bless $self;
|
---|
83 | }
|
---|
84 |
|
---|
85 | sub convert_post_process_old
|
---|
86 | {
|
---|
87 | my $self = shift (@_);
|
---|
88 | my ($conv_filename) = @_;
|
---|
89 |
|
---|
90 | my $outhandle=$self->{'outhandle'};
|
---|
91 |
|
---|
92 | my ($language, $encoding) = $self->textcat_get_language_encoding ($conv_filename);
|
---|
93 |
|
---|
94 | # read in file ($text will be in utf8)
|
---|
95 | my $text = "";
|
---|
96 | $self->read_file ($conv_filename, $encoding, $language, \$text);
|
---|
97 |
|
---|
98 | # turn any high bytes that aren't valid utf-8 into utf-8.
|
---|
99 | #unicode::ensure_utf8(\$text);
|
---|
100 |
|
---|
101 | # Write it out again!
|
---|
102 | #$self->utf8_write_file (\$text, $conv_filename);
|
---|
103 | }
|
---|
104 |
|
---|
105 | sub get_default_process_exp {
|
---|
106 | my $self = shift (@_);
|
---|
107 | return q^(?i)\.xls$^;
|
---|
108 | }
|
---|
109 |
|
---|
110 |
|
---|
111 | 1;
|
---|